Comparative Analysis of MobileNetV2, Xception, and EfficientNet for Batik Pattern Classification
DOI:
https://doi.org/10.30871/jaic.v10i4.13639Keywords:
Batik, Convolution Neural Network, MobileNetV2, Xception, EfficientNetAbstract
Indonesia boasts a rich cultural heritage in the form of batik, which has gained international recognition. However, the wide variety of batik motifs makes visual identification difficult for both locals and tourists. The limitations of manual observation and a lack of understanding regarding the significance behind each design pose a significant barrier to cultural preservation in the digital age. This study aims to conduct a comparative analysis of Deep Learning models to identify the most effective architecture for automatically classifying batik motifs. The method employed involved comparing three Convolutional Neural Network architectures: MobileNetV2, Xception, and EfficientNet. This study was conducted using a dataset containing 3,700 batik images that had been processed through a careful data distribution process. The primary objective of this evaluation is to find the optimal balance between high classification accuracy and efficient use of computational resources, enabling implementation on platforms with limited specifications. The results of this study indicate that these models can recognize complex batik patterns with outstanding validation accuracy rates ranging from 98% to 100%. These findings provide a strong technical foundation for selecting the most appropriate model architecture for developing intelligent systems aimed at preserving traditional batik. This study also shows that MobileNetv2 is the most optimal model architecture because it achieves a perfect balance between 100% accuracy and the fastest total inference time of 36.74 seconds, with an average inference time per sample of 0.0525 seconds. It is hoped that this research will make the batik identification process faster, more accurate, and accessible to the general public, thereby supporting the sustainability of Indonesia’s cultural heritage.
Downloads
References
[1] K. Kusnadi, “Exploring character education through batik Pekalongan local wisdom: An innovative approach to character learning,” Jurnal Civics: Media Kajian Kewarganegaraan, vol. 20, no. 2, pp. 223–235, Oct. 2023, doi: 10.21831/jc.v20i2.57000.
[2] D. Gede, T. Meranggi, N. Yudistira, and Y. A. Sari, “Batik Classification Using Convolutional Neural Network with Data Improvements,” International Journal on Informatics Visualization, Mar. 2022, doi: http://dx.doi.org/10.30630/joiv.6.1.716.
[3] A. Oktarino, Y. Desnita Tasri, and A. Efendi, “Identification of Batik Motif Based Deep Learning- Convolutional Neural Network Approach,” Journal of Ocean, Mechanical and Aesrospace, vol. 68, no. 3, Nov. 2024, doi: http://dx.doi.org/10.36842/jomase.v68i3.381.
[4] I. I’aza, T. Hosen, and S. A. Kamaruddin, “Batik Pattern Classification Using Machine Learning Approaches,” Applied Mathematics and Computational Intelligence, 2024, doi: https://doi.org/10.58915/amci.v13i3.690.
[5] U. Muhdhor and Y. Yohannes, “Evaluation of MobileNet-Based Deep Features for Yogyakarta Traditional Batik Motif Classification,” Sinkron : Jurnal dan Penelitian Teknik Informatika, vol. 10, no. 1, pp. 389–395, Jan. 2026, doi: 10.33395/sinkron.v10i1.15668.
[6] E. Utaminingsih and I. Sahputra, “Automated Recognition of Batik Aceh Patterns Using Machine Learning Techniques,” Brilliance: Research of Artificial Intelligence, vol. 4, no. 2, pp. 619–624, Nov. 2024, doi: 10.47709/brilliance.v4i2.4831.
[7] D. A. Ramadhan and D. Ramadhani, “Classification of Riau Batik Motifs Using the Convolutional Neural Network (CNN) Algorithm,” International Journal of Electrical, Energy and Power System Engineering, vol. 7, no. 3, pp. 201–211, Nov. 2024, doi: 10.31258/ijeepse.7.3.201-211.
[8] R. S. Putra, M. M. Al Haromainy, and A. Junaidi, “Classification of Jombang Batik Motifs Using Ensemble Convolutional Neural Network,” Bit-Tech (Binary Digital - Technology), vol. 8, no. 2, pp. 2102–2112, Dec. 2025, doi: 10.32877/bt.v8i2.3204.
[9] B. Sunarko et al., “Identification of the Sub-motifs of Batik Kawung Using Deep Learning,” MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer, vol. 25, no. 2, pp. 299–310, Mar. 2026, doi: 10.30812/matrik.v25i2.5818.
[10] E. Khoirunnisa et al., “Enhanced Semarang Batik Classification using MobileNetV2 and Data Augmentation,” Sinkron : Jurnal dan Penelitian Teknik Informatika, vol. 9, no. 1, pp. 43–54, Jan. 2025, doi: 10.33395/sinkron.v9i1.14308.
[11] M. Rafli, D. A. Prasetya, and K. M. Hindrayani, “Optimisation of Hyperparameter Tuning and Optimiser on MobileNetV2 for Batik Parang Classification,” Bit-Tech (Binary Digital - Technology), vol. 8, no. 3, pp. 3542–3552, Apr. 2026, doi: 10.32877/bt.v8i3.3576.
[12] A. Nurcahyo, N. Ishartono, A. Y. C. Pratiwi, and M. Waluyo, “Exploration Of Mathematical Concepts In Batik Truntum Surakarta,” Infinity Journal of Mathematics Education, vol. 13, no. 2, pp. 457–475, Sep. 2024, doi: 10.22460/infinity.v13i2.p457-476.
[13] M. Idhom, D. A. Prasetya, P. A. Riyantoko, T. M. Fahrudin, and A. P. Sari, “Pneumonia Classification Utilizing VGG-16 Architecture and Convolutional Neural Network Algorithm for Imbalanced Datasets,” TIERS Information Technology Journal, vol. 4, no. 1, pp. 73–82, Jun. 2023, doi: 10.38043/tiers.v4i1.4380.
[14] H. Sastypratiwi and H. Muhardi, “Batik Recognition and Classification Using Transfer Learning and MobileNet Approach,” International Journal on Informatics Visualization, Dec. 2024, doi: http://dx.doi.org/10.62527/joiv.8.4.2407.
[15] L. A. Latumakulita, “Pattern Recognition of Puta Dino Fabric Using Web-Based Convolutional Neural Network Method,” Journal of Applied Data Sciences, vol. 7, no. 2, pp. 1020–1035, May 2026, doi: 10.47738/jads.v7i2.1103.
[16] S. Suyahman and A. Hapsari, “VGG-Based Feature Extraction for Classifying Traditional Batik Motifs Using Machine Learning Models,” Preservation, Digital Technology and Culture, vol. 54, no. 3, pp. 215–222, Oct. 2025, doi: 10.1515/pdtc-2025-0009.
[17] M. S. Huda, H. Endah Wahanani, and F. T. Anggraeny, “Optimizing the ResNet50 Model with Five Optimizers for Detecting Rice Leaf Diseases,” Bit-Tech (Binary Digital - Technology), vol. 8, no. 2, pp. 2285–2296, Dec. 2025, doi: 10.32877/bt.v8i2.3232.
[18] E. A. Nabila, C. A. Sari, E. H. Rachmawanto, and M. Doheir, “A Good Performance of Convolutional Neural Network Based on AlexNet in Domestic Indonesian Car Types Classification,” Advance Sustainable Science Engineering and Technology, vol. 5, no. 3, p. 0230302, Oct. 2023, doi: 10.26877/asset.v5i3.16854.
[19] S. S. F. Ardyani and C. A. Sari, “A Web-Based for Demak Batik Classification Using VGG16 Convolutional Neural Network,” Advance Sustainable Science, Engineering and Technology, vol. 6, no. 4, pp. 0240406-01-0240406–09, Aug. 2024, doi: 10.26877/asset.v6i4.771.
[20] A. Akbar, M. Perdana, M. Fajar, and A. Muis Mappalotteng, “Enhancing Batik Classification Leveraging CNN Models and Transfer Learning,” International Journal on Informatics Visualization, May 2025, doi: http://dx.doi.org/10.62527/joiv.9.3.2535.
[21] E. Yulia Puspaningrum, B. Eden William Asrul, N. -Veteran, J. Timur, J. Adiyaksa Baru No, and J. Raya Rungkut Madya No, “Optimization of CNN Activation Functions using Xception for South Sulawesi Batik Classification,” Sistematis: Journal Sistem Informasi, 2025, doi: https://doi.org/10.32520/stmsi.v14i5.5281.
[22] B. J. Filia et al., “Improving Batik Pattern Classification using CNN with Advanced Augmentation and Oversampling on Imbalanced Dataset,” in Procedia Computer Science, Elsevier B.V., 2023, pp. 508–517. doi: 10.1016/j.procs.2023.10.552.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Maxentia Kathleen, Christy Atika Sari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
